© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6635
    Prev
    Next
    INDEX
    Explanations

    say ending with 'landers','.S', 'us'

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dır
    -0.08
     dáv
    -0.08
     vors
    -0.08
     clown
    -0.08
    bad
    -0.07
     മണിക്ക
    -0.07
    -Cl
    -0.07
    цо
    -0.07
     পরীক্ষা
    -0.07
     velha
    -0.07
    POSITIVE LOGITS
     impactos
    0.08
     impression
    0.08
     Impression
    0.08
     impacts
    0.08
    ความคิดเห็น
    0.08
    Inspired
    0.07
    мі
    0.07
     Depends
    0.07
     นิ
    0.07
    ферен
    0.07
    Activations Density 0.000%

    No Known Activations